| Project/Area Number |
18K18071
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 61010:Perceptual information processing-related
|
|---|
| Research Institution | National Institute of Advanced Industrial Science and Technology |
|---|
Principal Investigator |
Sakurada Ken 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (70773670)
|
|---|
| Project Period (FY) |
2018-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2018: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
|
|---|
| Keywords | SLAM / 変化検出 / 深層学習 / 3Dモデリング / Visual SLAM / 4D Visual SLAM |
|---|
| Outline of Final Research Achievements |
In this study, we developed methods of change detection and 3D modeling for the 4D Visual SLAM system. The papers of these methods have been accepted by top-tier computer vision and robotics conferences, such as CVPR, ICRA, ICCVW, and ACCV. Concretely, we developed an accurate change detection method that can be applied to the case when only a few negative samples are available (CVPR2019) and one that can not only detect but also classify scene changes (ICRA2020). Moreover, we developed 3D modeling methods based on multi-view geometry (ACCV2018) and convolutional neural networks (ICCVW2019).
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究により，近い将来実用化される自動運転やAR，サービスロボットで必要な大規模な3Dマップを構築する上で，データ容量や計測効率を大幅に向上させることが可能となる．この利点は，研究室環境のみで行われてきた技術を社会実装する上で極めて重要な要素である．
|
